FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200370223> ?p ?o ?g. }

• W3200370223 endingPage "201" @default.
• W3200370223 startingPage "190" @default.
• W3200370223 abstract "Methods based on Graph Convolutional Networks(GCN) for skeleton-based action recognition have achieved great success due to their ability to exploit graph structural information from skeleton data. Recently, the bone information has attracted considerable attention as an effective modality which complements the more conventional joint information for action recognition. However, most existing GCN-based methods extract the joint and bone features with two separate GCN networks, ignoring the dependencies between them. In this paper, a novel GCN model is proposed to exploit the information across joints, bones and their relationship collaboratively on a single undirected graph instead of two separate networks. We call the proposed model Vertex-Edge Graph Convolutional Network (VE-GCN) since it conducts the graph convolution operation on the sampling area containing the designated vertexes from joints and edges from bones, respectively. In addition to conducting the Vertex-Edge graph convolution based on the physical connections of the skeleton, we further apply the Vertex-Edge graph convolution to the non-physical joint-joint and joint-bone connections to capture the distal dependencies, and then the convolution results on the non-physical connections are incorporated into the VE-GCN. Moreover, the Conditional Random Field (CRF) is adopted as the loss function to achieve the task of action recognition. Experimental results on four challenging benchmarks (NTU RGB+D, NTU RGB+D 120, N-UCLA, SYSU) show that the proposed model achieves state-of-the-art performance." @default.
• W3200370223 created "2021-09-27" @default.
• W3200370223 creator A5001287866 @default.
• W3200370223 creator A5005495118 @default.
• W3200370223 creator A5025035701 @default.
• W3200370223 creator A5051363890 @default.
• W3200370223 creator A5069518008 @default.
• W3200370223 date "2021-11-01" @default.
• W3200370223 modified "2023-10-16" @default.
• W3200370223 title "Integrating vertex and edge features with Graph Convolutional Networks for skeleton-based action recognition" @default.
• W3200370223 cites W1893516992 @default.
• W3200370223 cites W2162670331 @default.
• W3200370223 cites W2313903725 @default.
• W3200370223 cites W2342650642 @default.
• W3200370223 cites W2510185399 @default.
• W3200370223 cites W2523592150 @default.
• W3200370223 cites W2583815496 @default.
• W3200370223 cites W2593146028 @default.
• W3200370223 cites W2603861860 @default.
• W3200370223 cites W2613570903 @default.
• W3200370223 cites W2736334449 @default.
• W3200370223 cites W2778523960 @default.
• W3200370223 cites W2798644314 @default.
• W3200370223 cites W2799211965 @default.
• W3200370223 cites W2868755588 @default.
• W3200370223 cites W2884286326 @default.
• W3200370223 cites W2940457086 @default.
• W3200370223 cites W2944006115 @default.
• W3200370223 cites W2948058585 @default.
• W3200370223 cites W2948246283 @default.
• W3200370223 cites W2950697450 @default.
• W3200370223 cites W2963076818 @default.
• W3200370223 cites W2963091558 @default.
• W3200370223 cites W2963369114 @default.
• W3200370223 cites W2963465695 @default.
• W3200370223 cites W2964134613 @default.
• W3200370223 cites W2970934252 @default.
• W3200370223 cites W2991376513 @default.
• W3200370223 cites W2996835428 @default.
• W3200370223 cites W2997769980 @default.
• W3200370223 cites W2998934002 @default.
• W3200370223 cites W3000832091 @default.
• W3200370223 cites W3034999503 @default.
• W3200370223 cites W3035050855 @default.
• W3200370223 cites W3035149912 @default.
• W3200370223 cites W3035225512 @default.
• W3200370223 cites W3040842087 @default.
• W3200370223 cites W3043878998 @default.
• W3200370223 cites W3090509403 @default.
• W3200370223 cites W3098538019 @default.
• W3200370223 cites W3099037876 @default.
• W3200370223 cites W3102322242 @default.
• W3200370223 doi "https://doi.org/10.1016/j.neucom.2021.09.034" @default.
• W3200370223 hasPublicationYear "2021" @default.
• W3200370223 type Work @default.
• W3200370223 sameAs 3200370223 @default.
• W3200370223 citedByCount "9" @default.
• W3200370223 countsByYear W32003702232022 @default.
• W3200370223 countsByYear W32003702232023 @default.
• W3200370223 crossrefType "journal-article" @default.
• W3200370223 hasAuthorship W3200370223A5001287866 @default.
• W3200370223 hasAuthorship W3200370223A5005495118 @default.
• W3200370223 hasAuthorship W3200370223A5025035701 @default.
• W3200370223 hasAuthorship W3200370223A5051363890 @default.
• W3200370223 hasAuthorship W3200370223A5069518008 @default.
• W3200370223 hasConcept C132525143 @default.
• W3200370223 hasConcept C153180895 @default.
• W3200370223 hasConcept C154945302 @default.
• W3200370223 hasConcept C2777212361 @default.
• W3200370223 hasConcept C2987834672 @default.
• W3200370223 hasConcept C41008148 @default.
• W3200370223 hasConcept C45347329 @default.
• W3200370223 hasConcept C50644808 @default.
• W3200370223 hasConcept C80444323 @default.
• W3200370223 hasConcept C80899671 @default.
• W3200370223 hasConcept C81363708 @default.
• W3200370223 hasConceptScore W3200370223C132525143 @default.
• W3200370223 hasConceptScore W3200370223C153180895 @default.
• W3200370223 hasConceptScore W3200370223C154945302 @default.
• W3200370223 hasConceptScore W3200370223C2777212361 @default.
• W3200370223 hasConceptScore W3200370223C2987834672 @default.
• W3200370223 hasConceptScore W3200370223C41008148 @default.
• W3200370223 hasConceptScore W3200370223C45347329 @default.
• W3200370223 hasConceptScore W3200370223C50644808 @default.
• W3200370223 hasConceptScore W3200370223C80444323 @default.
• W3200370223 hasConceptScore W3200370223C80899671 @default.
• W3200370223 hasConceptScore W3200370223C81363708 @default.
• W3200370223 hasFunder F4320334593 @default.
• W3200370223 hasLocation W32003702231 @default.
• W3200370223 hasOpenAccess W3200370223 @default.
• W3200370223 hasPrimaryLocation W32003702231 @default.
• W3200370223 hasRelatedWork W2964954556 @default.
• W3200370223 hasRelatedWork W2965803933 @default.
• W3200370223 hasRelatedWork W3019910406 @default.
• W3200370223 hasRelatedWork W4211202157 @default.
• W3200370223 hasRelatedWork W4287181611 @default.
• W3200370223 hasRelatedWork W4293226380 @default.
• W3200370223 hasRelatedWork W4301046126 @default.

• next